Building Safer Sites: A Large-Scale Multi-Level Dataset for Construction Safety Research

2025-08-08

AI Summary

Existing construction safety datasets are limited in scale and diversity, hindering deep analytical insights. Method: We introduce CSDataset—the first large-scale, multi-level construction safety dataset—systematically integrating OSHA incident, inspection, and violation records. It enables unified modeling and cross-level association analysis across event, firm, and temporal dimensions, jointly representing structured attributes and unstructured text. We further propose a heterogeneous data processing framework that synergistically combines machine learning and large language models, augmented with causal inference techniques. Contribution/Results: Our analysis reveals that complaint-driven inspections reduce subsequent incident rates by 17.3%. The dataset and code are publicly released to support risk prediction, causal attribution, and intervention strategy optimization. CSDataset establishes a new empirical benchmark for construction safety research, facilitating rigorous, data-driven advancements in occupational safety science.

Technology Category

• Natural Language Processing: Safety and Robustness
• Machine Learning: Feature Construction/Reformulation
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Security and Privacy: Data transparency and provenance
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Web Mining and Content Analysis: Web data provenance, reliability, and authenticity

Abstract

Construction safety research is a critical field in civil engineering, aiming to mitigate risks and prevent injuries through the analysis of site conditions and human factors. However, the limited volume and lack of diversity in existing construction safety datasets pose significant challenges to conducting in-depth analyses. To address this research gap, this paper introduces the Construction Safety Dataset (CSDataset), a well-organized comprehensive multi-level dataset that encompasses incidents, inspections, and violations recorded sourced from the Occupational Safety and Health Administration (OSHA). This dataset uniquely integrates structured attributes with unstructured narratives, facilitating a wide range of approaches driven by machine learning and large language models. We also conduct a preliminary approach benchmarking and various cross-level analyses using our dataset, offering insights to inform and enhance future efforts in construction safety. For example, we found that complaint-driven inspections were associated with a 17.3% reduction in the likelihood of subsequent incidents. Our dataset and code are released at https://github.com/zhenhuiou/Construction-Safety-Dataset-CSDataset.

Problem

• Limited volume and diversity in construction safety datasets hinder analysis
• Need for comprehensive multi-level dataset integrating structured and unstructured data
• Lack of benchmarked approaches for construction safety risk mitigation

Innovation

• Multi-level dataset integrating structured and unstructured data
• Leverages machine learning and large language models
• Includes incidents, inspections, and violations from OSHA